Power inspection network performance evaluation method, equipment and medium

Abstract

The invention relates to an electric power inspection network performance evaluation method, equipment and a medium. The method comprises the following steps: hierarchically dividing an electric power inspection network into an access network, a transmission network and a core network; monitoring network performance parameters of the access network, the transmission network and the core network by using a communication equipment performance monitoring module; network performance parameters are preprocessed and then input into the BP neural network model with the parameters optimized through the genetic algorithm, performance evaluation values within a preset numerical value range are output, and a fitness function of the genetic algorithm is obtained by conducting weighted summation on model prediction accuracy and a network toughness value based on scene adjustment factors; the network toughness value is determined based on a failure recovery time indicator and a service degradation degree. Compared with the prior art, the method not only can ensure the accuracy of network performance evaluation, but also can match the toughness requirements of the network in different application scenes, and has the advantages of accurate prediction, high adaptability to different scenes and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power communication network, and in particular to a power inspection network performance evaluation method, device and medium. BACKGROUND

[0002] As a core link to ensure the safe and stable operation of the power grid, power inspection is gradually transforming towards intelligentization and digitization. In recent years, intelligent inspection technologies centered on unmanned aerial vehicles, intelligent robots, and Internet of Things sensors have been widely applied. These technologies have higher requirements for the real-time performance, reliability, and coverage capability of communication networks. To meet the diverse needs in complex power scenarios, power inspection networks gradually adopt a hybrid networking mode, which integrates 5G, wired networks, wireless private networks, and other heterogeneous communication technologies, combines industrial control networks and Internet of Things technologies, and builds a ubiquitous interconnected communication architecture.

[0003] However, the network performance in a hybrid networking environment is affected by factors such as multi-technology coordination mechanisms, dynamic topology changes, and heterogeneous protocol compatibility, resulting in potential problems such as bandwidth fluctuations, latency jitter, and data packet loss, which may directly affect the data backhaul quality, remote control accuracy, and fault warning timeliness of inspection devices, thereby threatening the safe operation of the power system. Therefore, it is necessary to evaluate the network performance.

[0004] Chinese patent CN108400895A discloses a BP neural network security situation evaluation algorithm based on genetic algorithm improvement. By reasonably constructing a network security situation evaluation model and relying on the powerful self-learning ability of neural networks, the BP neural network is applied to the evaluation of network security situation. Meanwhile, to address the defects of neural network algorithms, such as being limited to local minimum values and slow convergence speed, a genetic algorithm is introduced to optimize the weights of the BP neural network, accelerate the convergence speed of the BP neural network, and improve the accuracy and efficiency of the BP neural network in evaluating network security situation, thereby effectively solving the problems of low efficiency and uncertainty of the results of network security situation evaluation using a simple neural network. However, this method only evaluates the security situation and cannot cover multiple aspects of network performance evaluation, especially lacking evaluation of network resilience, which makes it difficult to cope with dynamic fault scenarios. Moreover, this method does not specifically divide the network levels, so it cannot determine the corresponding differentiated performance indicators for each level based on their characteristics, affecting the effectiveness of the prediction results.

[0005] Therefore, there is currently a lack of a network performance evaluation method that can distinguish between different levels of power inspection networks and specifically consider the characteristics and network resilience of different levels. SUMMARY

[0006] The present application aims to provide a power inspection network performance evaluation method, device and medium to overcome the defects of the prior art.

[0007] The object of the present application can be achieved by the following technical solutions: According to the first aspect of the present application, a power inspection network performance evaluation method is provided, which comprises the following steps: The power inspection network hierarchy is divided into an access network, a transmission network and a core network. The network performance parameters of the access network, the transmission network and the core network are monitored using a communication device performance monitoring module. After preprocessing the network performance parameters, the BP neural network model optimized by the genetic algorithm is input, and the performance evaluation value within the preset numerical range is output, wherein the fitness function of the genetic algorithm is based on the scene adjustment factor to weight and sum the model prediction accuracy and the network resilience value, and the network resilience value is determined based on the fault recovery time index and the service degradation degree.

[0008] The access network includes a communication network, a wireless private network and a 4G / 5G virtual private network, which is used to realize the safe and reliable access of communication terminals; the transmission network is used to transmit the data of the access layer to the core network; the core network includes a router and an enterprise middle station, wherein the router is used to receive the terminal data transmitted by the transmission network and send the data to the enterprise middle station, and the enterprise middle station is used to provide the data to the upper business system for analysis, and is responsible for managing and issuing instructions to the terminal equipment.

[0009] The network performance monitoring parameters of the access network are divided into local communication layer network performance monitoring parameters and remote communication layer network performance monitoring parameters, wherein, The local communication layer network performance monitoring parameters include wired access network network performance monitoring parameters and wireless access network network performance monitoring parameters, the wired access network network performance monitoring parameters include port bandwidth utilization, xPON received optical power and standby switching time, and the wireless access network network performance monitoring parameters include air interface connection rate, channel utilization, AP associated terminal quantity, throughput, delay, packet loss rate, concurrency rate and dual redundancy switching time. The remote communication layer network performance monitoring parameters include throughput, delay, packet loss rate, jitter, standby switching time and routing convergence time.

[0010] The network performance monitoring parameters of the transmission network include transmitted optical power, received optical power, optical signal-to-noise ratio, bit error rate, transmission delay, delay jitter and SDH protection switching time.

[0011] The network performance monitoring parameters of the core network include throughput, latency, latency jitter, ECMP error, CPU utilization, memory utilization, table item capacity usage, neighbor state and route convergence time.

[0012] The fitness function of the genetic algorithm is represented as: , Wherein, is a scene adjustment factor, which is determined according to the demand for prediction accuracy and resilience of different network scenes; is the prediction error of the normal sample, which is the network feature vector after preprocessing the network performance parameters; is the fault recovery time index of the virtual fault sample, is the service degradation degree of the virtual fault sample, , , is the standard fault recovery time, is the fault recovery time of the virtual fault sample, is the standard service rate, is the service rate when the virtual fault sample is faulty; the generation method of the virtual fault sample is: for normal samples Wherein, is the number of network performance monitoring parameters, and the virtual fault sample is generated by a neighborhood disturbance operator , , is the fault sensitivity coefficient of the network performance monitoring parameter , is the fault intensity, is a random disturbance.

[0013] The genetic algorithm performs the following steps to optimize the BP neural network model parameters: The weight parameters and bias parameters in the BP neural network model are real coded and mapped to the chromosomes of the genetic algorithm; Population initialization is performed, and a fitness function is defined; Perform population update by genetic operation, the genetic operation includes crossover, mutation and selection, wherein the crossover probability is determined based on the regulatory gene coding, the crossover operation is performed, the activity value of the regulatory gene coding is determined based on the derivative of the loss function of the BP neural network to the gene in the chromosome; Perform mutation operation on the original gene based on mutation strength, the mutation strength is determined based on the contribution degree of the gene to the virtual fault sample; the selection operation is performed based on individual fitness ranking; When the number of iterations reaches a preset value or the fitness of the optimal individual changes less than a preset threshold for a preset number of iterations, the iteration is terminated, the optimal chromosome is output, and the optimized model parameters are obtained, otherwise, the genetic operation is returned to perform population updating.

[0014] The crossover operation comprises the following steps: The activity value of the i-th gene is calculated : , wherein, L is a loss function of the BP neural network on normal samples, represents a parameter value of the i-th gene, and M is the total number of genes, that is, the total number of parameters to be optimized of the BP neural network model; The regulatory gene code of the i-th gene is determined based on the activity value , , wherein, a is a preset threshold, is the regulatory gene code of the i-th gene; The crossover probability is determined based on the regulatory gene code , , wherein, , is a preset weight, satisfying and ; respectively represent the regulatory gene code of the parent and the parent , is the crossover probability of the i-th gene of the parent and the parent for the crossover operation; The mutation operation comprises the following steps: The i-th gene is randomly disturbed, and the change rate of the virtual failure sample loss function is calculated to obtain the contribution degree of the i-th gene to the virtual failure sample , wherein, represents a loss function of the BP neural network on the virtual failure sample, represents a random disturbance to the gene, is a preset value for preventing the denominator from being 0; The mutation strength is calculated based on the contribution degree, and the original gene is subjected to mutation operation ​​​​​​ , wherein, is the gene after mutation operation, is the mutation intensity, quantified by the contribution degree is obtained by segment mapping.

[0015] According to a second aspect of the present application, an electronic device is provided, comprising a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method when executing the program.

[0016] According to a third aspect of the present application, a computer readable storage medium is provided, having stored thereon a computer program, the program being executed by a processor to implement the method.

[0017] Compared with the prior art, the present application has the following beneficial effects: (1) The present application divides the network into an access network, a transmission network and a core network, respectively monitors the performance indicators of the corresponding levels, and can monitor the performance parameters of different components in the network for different purposes, thereby improving the accuracy and effectiveness of subsequent performance evaluation.

[0018] (2) The fitness function of the prior art is only based on prediction error as the only evaluation standard, which is easy to lead to the selection of parameter combinations with high prediction accuracy but unable to match the actual running resilience demand of the network. The setting of the fitness function of the present application can ensure that the BP neural network parameters optimized by the genetic algorithm can not only ensure the accuracy of network performance (such as time delay and packet loss rate) prediction, but also match the resilience demand of the network under fault, so that the optimized BP neural network model is more suitable for the actual network operation and maintenance scene. Moreover, through the scene adjustment factor which can be dynamically adjusted in the fitness function, the same fitness function can adapt to different types of network performance evaluation scenes, improving the overall applicability and robustness of the method.

[0019] (3) The present application improves the crossover and mutation process of the genetic algorithm. The crossover operation can accurately evaluate the effect of parameters on the normal operation state evaluation of the power inspection network through the measurement of the activity value, so as to give higher crossover probability to high-activity genes, speed up the convergence efficiency in normal scenes, and reserve a certain crossover probability for low-activity genes to keep the possibility of exploring new parameter combinations and avoid falling into local optimum too early. The mutation operation quantifies the influence degree of a single gene on the fault scene evaluation accuracy through the contribution degree. The greater the contribution degree, the more critical the gene, and thus the greater the mutation intensity after segment mapping. The high mutation intensity of the key gene can more efficiently explore better parameter combinations and quickly improve the evaluation accuracy in the fault scene. The small mutation intensity of the non-key gene avoids meaningless disturbance and retains the optimized parameter characteristics in normal scenes, thereby improving the optimization efficiency of the genetic algorithm as a whole. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 Flow chart of the method of the present application; Figure 2 Flow chart of the genetic algorithm of the present application; Figure 3 Flow chart of the crossover operation of the present application; Figure 4 Flow chart of the mutation operation of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0022] Unless otherwise defined, technical terms or scientific terms used in the present application should be understood as their common meanings to those skilled in the art. The terms "one", "a", "an", "the", and similar terms in the present application do not represent quantity limitation, but can represent singular or plural. The terms "include", "contain", "have", and any variations thereof in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device including a series of steps or modules (units) is not limited to the listed steps or units, but can further include steps or units not listed, or can further include other steps or units inherent to the process, method, product, or device. The terms "connect", "connected", "couple", and similar terms in the present application are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The term "multiple" in the present application refers to two or more. The term "and / or" describes the association relationship between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects. The terms "first", "second", "third", and the like in the present application are only to distinguish similar objects, and do not represent a specific order of the objects.

[0023] Embodiment 1 The present embodiment provides a power inspection network performance evaluation method, as shown in Figure 1 The method comprises the following steps: S1, the power inspection network level is divided into access network, transmission network, and core network.

[0024] In this embodiment, the access network includes a communication network, a wireless private network and a 4G / 5G virtual private network, which are used to realize secure and reliable access of the communication terminal; the transmission network is used to transmit data of the access layer to the core network, mainly using optical fiber transmission technologies such as SDH and OTN; the core network includes a router and an enterprise middle station, wherein the router is used to receive terminal data transmitted by the transmission network and send the data to the enterprise middle station, and the enterprise middle station is used to provide the data to an upper-layer business system for analysis and is responsible for management and issuing instructions to the terminal equipment.

[0025] S2, monitoring network performance parameters of the access network, the transmission network and the core network by using a communication device performance monitoring module.

[0026] According to the network level, the network performance parameters are divided into access network network performance monitoring parameters, transmission network network performance monitoring parameters and core network network performance monitoring parameters.

[0027] In a preferred embodiment, the network performance monitoring parameters of the access network are divided into local communication layer network performance monitoring parameters and remote communication layer network performance monitoring parameters, wherein, The local communication layer network performance monitoring parameters include wired access network network performance monitoring parameters and wireless access network network performance monitoring parameters, the wired access network network performance monitoring parameters include port bandwidth utilization, xPON received optical power and master-slave switching time, and the wireless access network network performance monitoring parameters include air interface link establishment rate, channel utilization, AP associated terminal quantity, throughput, time delay, packet loss rate, concurrency rate and dual-redundancy switching time. The remote communication layer network performance monitoring parameters include throughput, time delay, packet loss rate, jitter, master-slave switching time and route convergence time.

[0028] The network performance monitoring parameters of the transmission network include transmitted optical power, received optical power, optical signal-to-noise ratio, bit error rate, transmission time delay, time delay jitter and SDH protection switching time.

[0029] The network performance monitoring parameters of the core network include throughput, time delay, time delay jitter, ECMP error, CPU utilization, memory utilization, table item capacity utilization, neighbor state and route convergence time.

[0030] S3, inputting the network performance parameters after preprocessing into a BP neural network model optimized by using a genetic algorithm, and outputting performance evaluation values in a preset numerical range.

[0031] First, the network topology of the BP neural network model is designed; this invention does not limit its specific structure. In one preferred embodiment, the BP neural network model employs multiple hidden layers, with the initial number of nodes in the hidden layers determined by an empirical formula. The activation function of the output layer is Linear, outputting continuous performance evaluation scores, and the loss function is measured by Mean Squared Error (MSE). In another embodiment, the output layer of the model can also use a softmax activation function to output different classification levels of network performance; this can be set according to the needs of the actual application scenario.

[0032] For the BP neural network model, the first Layer There are neurons, and their weighted input values ​​are: , Its activation output value is: , in, For the first Layer The neuron connects to the previous layer. Weights between neurons; For the first Layer Bias of each neuron; For activation functions; For the first Layer The output of each neuron.

[0033] During model training, forward propagation begins, calculating the predicted output through the hidden and output layers. The error is then calculated by comparing this predicted output with the actual target output. In the backpropagation phase, based on the error, gradient descent is used to propagate the error layer by layer from the output layer to the hidden layers, continuously adjusting the weights and biases to reduce the error. This process involves the application of the chain rule, updating the weights and biases of each neuron by calculating gradients.

[0034] like Figure 2 As shown, the genetic algorithm performs the following steps to optimize the parameters of the BP neural network model: Step 1) Encode the weight parameters and bias parameters in the BP neural network model with real numbers and map them to chromosomes in the genetic algorithm.

[0035] Step 2) Initialize the population and define the fitness function.

[0036] In this embodiment, the fitness function of the genetic algorithm is obtained by weighting and summing the model prediction accuracy and network resilience value based on the scene adjustment factor. The network resilience value is determined based on the fault recovery time index and service degradation degree. , wherein, is a scene adjustment factor, determined according to the requirements of prediction accuracy and resilience in different network scenes, for example, for the industrial control network scene, the prediction accuracy weight needs to be reduced and the resilience weight needs to be increased, ; for the civil broadband network scene, the prediction accuracy weight needs to be increased and the resilience weight needs to be reduced, ; is the prediction error of the normal sample, the normal sample being a network feature vector after pre-processing of the network performance parameter; is the fault recovery time index of the virtual fault sample, is the service degradation degree of the virtual fault sample, , , is the standard fault recovery time, is the fault recovery time of the virtual fault sample, is the standard service rate, is the service rate when the virtual fault sample is in fault. The fault recovery time and the service degradation degree are quantified as two indexes, which are then integrated into the fitness function, so as to improve the consideration of network resilience in the parameter optimization result.

[0037] In the embodiment, the generation method of the virtual fault sample is: for the normal sample wherein, is the number of network performance monitoring parameters, the virtual fault sample being generated by a neighborhood disturbance operator , , is the fault sensitivity coefficient of the network performance monitoring parameter , is the fault intensity, taking a value of [0.2, 0.5], is a random disturbance obeying N (0, 1) distribution.

[0038] Step 3) performing genetic operation to update the population, the genetic operation including crossover, mutation and selection.

[0039] Step 4) terminating the iteration when the number of iterations reaches a preset value or the fitness of the optimal individual changes by less than a preset threshold value for a preset number of generations, outputting the optimal chromosome to obtain the optimized model parameters, otherwise, returning to perform the genetic operation to update the population.

[0040] Embodiment 2 This embodiment, based on Embodiment 1, provides an improved scheme for crossover and mutation operations in a genetic algorithm. Specifically, the crossover probability is adaptively determined based on the coding of regulatory genes, and the crossover operation is performed. The coding of regulatory genes is determined based on the activity value defined by the derivative of the loss function of the BP neural network with respect to genes in the chromosome. The mutation operation is performed on the original genes based on the mutation intensity, which is determined based on the contribution of the gene to the virtual fault samples. The selection operation is performed based on the fitness ranking of individuals.

[0041] like Figure 3 As shown, the crossover operation includes the following steps: A1, calculate the... The activity value of each gene : , in, Let be the loss function of the BP neural network on normal samples. Indicates the first The parameter values ​​of each gene, where M is the total number of genes, i.e., the total number of parameters to be optimized in the BP neural network model; A2, Based on the activity value, determine the encoding of the regulatory gene: , in, The preset threshold, For the first The regulatory gene encoding each gene; A3, Determine the crossover probability based on the coding of the aforementioned regulatory genes: , in, , For the preset weights, satisfy and ; Representing the father generation and father generation The regulatory gene encoding, For father and father generation The The crossover probability of a gene undergoing a crossover operation.

[0042] like Figure 4 As shown, the mutation operation includes the following steps: B1, for the first The genes are randomly perturbed, and the rate of change of the virtual fault sample loss function is calculated to obtain the th gene. The contribution of each gene to the virtual fault sample: , in, This represents the loss function of the BP neural network on virtual fault samples. This represents a random perturbation of the gene. This is a preset value used to prevent the denominator from being 0; B2, Calculate the mutation intensity based on the contribution, and perform mutation operations on the original gene: , in, This refers to the gene after the mutation operation. The strength of the variation is determined by the contribution. This is obtained by performing segmented mapping.

[0043] Example 3 This embodiment provides a method for preprocessing network performance parameters, based on embodiment 1.

[0044] This step involves decomposing the network performance parameters related to decision-making into multiple levels, then performing quantitative and qualitative analysis on them, using the analytic hierarchy process (AHP) to determine the weight of each parameter, and finally multiplying the weights by the initial network performance parameters as the input to the BP neural network model.

[0045] Further steps include: 1) For the same level indicators in the three network levels, perform pairwise comparisons to determine their relative importance. The specific determination method is shown in Table 1.

[0046] Table 1

[0047] 2) Construct a judgment matrix based on the determined relative importance. : , Among them, the judgment matrix The elements in the middle have the following properties: .

[0048] 3) Based on the judgment matrix ,get The largest eigenvalue and its corresponding eigenvectors : = , For eigenvectors After normalization, the resulting values ​​are the ranking weights of the relative importance of each network performance indicator within the same level.

[0049] 4) By calculating the consistency index Consistency ratio Check the consistency of the judgment matrix to ensure that the judgment result is reasonable.

[0050] , In the formula, is the order of the judgment matrix ; , In the formula, is a random consistency index, which is an average consistency index calculated by a large number of random matrices, and the value is shown in Table 2.

[0051] Table 2

[0052] If is less than 0.1, it is considered that the matrix has acceptable consistency.

[0053] Example 4 The electronic device includes a central processing unit (CPU) that can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or computer program instructions loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0054] A plurality of components in the device are connected to the I / O interface, including: an input unit such as a keyboard, a mouse, etc.; an output unit such as various types of displays, a speaker, etc.; a storage unit such as a magnetic disk, an optical disk, etc.; and a communication unit such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0055] The processing unit performs various methods and processes described above, such as methods S1-S3. For example, in some embodiments, methods S1-S3 can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the device via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1-S3 described above can be performed. Alternatively, in other embodiments, the CPU can be configured to perform methods S1-S3 by any other appropriate means (e.g., by means of firmware).

[0056] The functionality described above in this document can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program- specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0057] Program code for carrying out methods of the present application can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0058] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include, without limitation, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.

[0059] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for evaluating the performance of a power line inspection network, characterized in that, The method includes the following steps: The power inspection network is divided into access network, transmission network, and core network. The network performance parameters of the access network, transmission network, and core network are monitored using a communication equipment performance monitoring module. After preprocessing the network performance parameters, the data is input into a BP neural network model with optimized parameters using a genetic algorithm. The model outputs a performance evaluation value within a preset range. The fitness function of the genetic algorithm is obtained by weighted summation of the model prediction accuracy and network resilience value based on a scenario adjustment factor. The network resilience value is determined based on the fault recovery time index and service degradation degree.

2. The power inspection network performance evaluation method according to claim 1, characterized in that, The access network includes a communication network, a wireless private network, and a 4G / 5G virtual private network, used to enable secure and reliable access for communication terminals; the transmission network is used to transmit access layer data to the core network; the core network includes routers and an enterprise middleware platform, wherein the routers are used to receive terminal data from the transmission network and send the data to the enterprise middleware platform, and the enterprise middleware platform is used to provide the data to the upper-layer business system for analysis, and is also responsible for management and issuing instructions to terminal devices.

3. The power inspection network performance evaluation method according to claim 1, characterized in that, The network performance monitoring parameters of the access network are divided into local communication layer network performance monitoring parameters and remote communication layer network performance monitoring parameters, among which, The local communication layer network performance monitoring parameters include wired access network performance monitoring parameters and wireless access network performance monitoring parameters. The wired access network performance monitoring parameters include port bandwidth utilization, xPON received optical power, and primary / backup switchover time. The wireless access network performance monitoring parameters include air interface link establishment rate, channel utilization, number of AP associated terminals, throughput, latency, packet loss rate, concurrency rate, and dual redundancy switchover time. The network performance monitoring parameters for the remote communication layer include throughput, latency, packet loss rate, jitter, primary / backup switchover time, and routing convergence time.

4. The power inspection network performance evaluation method according to claim 1, characterized in that, The network performance monitoring parameters of the transmission network include transmitted optical power, received optical power, optical signal-to-noise ratio, bit error rate, transmission delay, delay jitter, and SDH protection switching time.

5. The power inspection network performance evaluation method according to claim 1, characterized in that, The network performance monitoring parameters of the core network include throughput, latency, latency jitter, ECMP error, CPU utilization, memory utilization, table capacity utilization, neighbor status, and route convergence time.

6. The power inspection network performance evaluation method according to claim 1, characterized in that, The fitness function of the genetic algorithm is expressed as: ， in, This is a scenario adjustment factor, determined based on the requirements of different network scenarios for prediction accuracy and resilience; The prediction error is for normal samples, which are network feature vectors after preprocessing of network performance parameters. For the fault recovery time index of virtual fault samples, The degree of service degradation for virtual fault samples. , , Standard fault recovery time, The fault recovery time for the virtual fault sample. For standard service rates, The service rate during a virtual fault sample failure; the method for generating the virtual fault sample is as follows: based on normal samples... ,in, To determine the number of network performance monitoring parameters, virtual fault samples are generated using the neighborhood perturbation operator. , , For network performance monitoring parameters The fault sensitivity coefficient, For fault intensity, It is a random perturbation.

7. The power inspection network performance evaluation method according to claim 1, characterized in that, The genetic algorithm performs the following steps to optimize the parameters of the BP neural network model: The weight parameters and bias parameters in the BP neural network model are encoded with real numbers and mapped to chromosomes in the genetic algorithm. Perform population initialization and define the fitness function; Genetic operations are performed to update the population, including crossover, mutation, and selection. Specifically, the crossover probability is adaptively determined based on the coding of regulatory genes, and the crossover operation is performed. The coding of regulatory genes is determined based on the activity value defined by the derivative of the gene in the chromosome using the loss function of a BP neural network. A mutation operation is performed on the original gene based on the mutation intensity, which is determined based on the gene's contribution to the virtual fault samples. A selection operation is performed based on the individual fitness ranking. The iteration terminates when the number of iterations reaches a preset value or the fitness change of the best individual in consecutive preset generations is less than a preset threshold, and the optimal chromosome is output to obtain the optimized model parameters. Otherwise, the process returns to perform genetic operations to update the population.

8. The power inspection network performance evaluation method according to claim 7, characterized in that, The crossover operation includes the following steps: Calculate the first The activity value of each gene : ， in, Let be the loss function of the BP neural network on normal samples. Indicates the first The parameter values ​​of each gene, where M is the total number of genes, i.e., the total number of parameters to be optimized in the BP neural network model; Based on the activity value, the coding of the regulatory gene is determined: ， in, The preset threshold, For the first The regulatory gene encoding each gene; The crossover probability is determined based on the coding of the aforementioned regulatory genes: ， in, , For the preset weights, satisfy and ; Representing the father generation and father generation The regulatory gene encoding, For father and father generation The The crossover probability of a gene undergoing a crossover operation; The mutation operation includes the following steps: For the first The genes are randomly perturbed, and the rate of change of the virtual fault sample loss function is calculated to obtain the th gene. The contribution of each gene to the virtual fault sample: ， in, This represents the loss function of the BP neural network on virtual fault samples. This represents a random perturbation of the gene. This is a preset value used to prevent the denominator from being 0; Based on the contribution, the mutation intensity is calculated, and the original gene is mutated. ， in, This refers to the gene after the mutation operation. The strength of the variation is determined by the contribution. This is obtained by performing segmented mapping.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 8.

Images